ComfyUI-3D-Pack

Make 3D assets generation in ComfyUI good and convenient as it generates image/video!

This is an extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc.) using cutting edge algorithms (3DGS, NeRF, etc.) and models (InstantMesh, CRM, TripoSR, etc.)

Features — Install — Roadmap — Development — Tips — Supporters

Install:

Can be installed directly from ComfyUI-Manager🚀

Alternatively you can download Comfy3D-WinPortable made by YanWenKun

• Pre-builds are available for:
• Windows 10/11
• Python 3.12
• CUDA 12.4
• torch 2.5.1+cu124
• install.py will download & install Pre-builds automatically according to your runtime environment, if it couldn't find corresponding Pre-builds, then build script will start automatically, if automatic build doesn't work for you, then please check out Semi-Automatic Build Guide
• If you have any missing node in any open Comfy3D workflow, try simply click Install Missing Custom Nodes in ComfyUI-Manager
• In case there is missing python library, you can check all the python dependencies of my dev environment
• If for some reason your comfy3d can't download pre-trained models automatically, you can always download them manually and put them in to correct folder under Checkpointsdirectory, but please DON'T overwrite any exist .json files
• Docker install please check DOCKER_INSTRUCTIONS.md
• Note: at this moment, you'll still need to install Visual Studio Build Tools for windows and install gcc g++ for Linux in order for InstantNGP & Convert 3DGS to Mesh with NeRF and Marching_Cubes nodes to work, since those two nodes used JIT torch cpp extension that builds in runtime, but I plan to replace those nodes

For manual install

# Fetch newest version of Comfy3D
cd Your ComfyUI Root Directory\ComfyUI\custom_nodes\
git clone https://github.com/MrForExample/ComfyUI-3D-Pack.git
cd ComfyUI-3D-Pack

# Install all dependencies
Your ComfyUI Root Directory\python_embeded\python.exe -s -m pip install -r requirements.txt
Your ComfyUI Root Directory\python_embeded\python.exe install.py

Features:

• For use cases please check out Example Workflows. [Last update: 5/June/2025]

• Note: you need to put Example Inputs Files & Folders under ComfyUI Root Directory\ComfyUI\input folder before you can run the example workflow

• PartCrafter: wgsxm/PartCrafter

• Two-model pipeline:
  • Single object mode:
  • Single image → 3D mesh with part segmentation
  • Output:
    • Merged full mesh
    • ZIP archive with individual part meshes
  • Scene mode:
  • Scene image → multiple 3D part meshes
  • Output:
    • Merged full scene mesh
    • ZIP archive with individual object meshes
• Model weights:
  • PartCrafter (object mode)
  • PartCrafter-Scene (scene mode)
• Workflows:
  • Single Object
  • Scene

• Hunyuan3D_2.1: Tencent-Hunyuan/Hunyuan3D-2.1
• Updated two-stage pipeline:
  • Single image → 3D mesh (shape generation)
  • 3D mesh + reference image → 3D mesh with RGB texture
• Model weights: https://huggingface.co/tencent/Hunyuan3D-2.1
• Workflows: Full, Shapegen, Texgen

• MV-Adapter: huanngzh/MV-Adapter
• Two generation methods:
  • IG2MV: Single image + 3D mesh to multi-view images
  • TG2MV: Text prompt + 3D mesh to multi-view images
  • Texturing: Grid image + 3D mesh to textured mesh
• Model weights: https://huggingface.co/huanngzh/mv-adapter
• Workflows: IG2MV, T2MV, Texturing

• Stable3DGen: Stable-X/Stable3DGen
• Two models pipeline:
  • Stable3DGen: Single image to 3D Mesh
  • StableNormal: Image processing for normal map generation
• Model weights:
  • Stable3DGen: https://huggingface.co/Stable-X/trellis-normal-v0-1
  • StableNormal: https://huggingface.co/Stable-X/yoso-normal-v1-8-1
• Workflow

• Hunyuan3D_V2: turbo, mini, fast, multiview
• Single image to 3D Mesh
• Multi-views to 3D Mesh with RGB texture
• Model weights: https://huggingface.co/tencent/Hunyuan3D-2, https://huggingface.co/tencent/Hunyuan3D-2mini
• Workflows

• TripoSG: VAST-AI-Research/TripoSG
• Single image (Reference or Scribble) to 3D Mesh
• Model weights: https://huggingface.co/VAST-AI/TripoSG, https://huggingface.co/VAST-AI/TripoSG-scribble

• TRELLIS: microsoft/TRELLIS
• Single image to 3D Mesh with RGB texture
• Model weights: https://huggingface.co/jetx/TRELLIS-image-large

• Hunyuan3D_V2 tencent/Hunyuan3D-2
• Two stages pipeline:
  1. Single image to 3D Mesh shape only
  2. 3D Mesh shape + Single reference image to 3D Mesh with RGB texture
• Model weights: https://huggingface.co/tencent/Hunyuan3D-2/tree/main
• Workflows

• Hunyuan3D_V1 tencent/Hunyuan3D-1
• Two stages pipeline:
  1. Single image to multi-views
  2. Multi-views to 3D Mesh with RGB texture
• Model weights: https://huggingface.co/tencent/Hunyuan3D-1/tree/main

• StableFast3D: Stability-AI/stable-fast-3d
• Single image to 3D Mesh with RGB texture
• Note: you need to agree to Stability-AI's term of usage before been able to download the model weights, if you downloaded model weights manually, then you need to put it under Checkpoints/StableFast3D, otherwise you can add your huggingface token in Configs/system.conf
• Model weights: https://huggingface.co/stabilityai/stable-fast-3d/tree/main

• CharacterGen: zjp-shadow/CharacterGen
• Single front view of a character with arbitrary pose
• Can combine with Unique3D workflow for better result
• Model weights: https://huggingface.co/zjpshadow/CharacterGen/tree/main

• Unique3D: AiuniAI/Unique3D
• Four stages pipeline:
  1. Single image to 4 multi-view images with resolution: 256X256
  2. Consistent Multi-view images Upscale to 512X512, super resolution to 2048X2048
  3. Multi-view images to Normal maps with resolution: 512X512, super resolution to 2048X2048
  4. Multi-view images & Normal maps to 3D mesh with texture
• To use the All stage Unique3D workflow, Download Models:
  • sdv1.5-pruned-emaonly and put it into Your ComfyUI root directory/ComfyUI/models/checkpoints
  • fine-tuned controlnet-tile and put it into Your ComfyUI root directory/ComfyUI/models/controlnet
  • ip-adapter_sd15 and put it into Your ComfyUI root directory/ComfyUI/models/ipadapter
  • OpenCLIP-ViT-H-14, rename it to OpenCLIP-ViT-H-14.safetensors and put it into Your ComfyUI root directory/ComfyUI/models/clip_vision
  • RealESRGAN_x4plus and put it into Your ComfyUI root directory/ComfyUI/models/upscale_models
• Model weights: https://huggingface.co/spaces/Wuvin/Unique3D/tree/main/ckpt

• Era3D MVDiffusion Model: pengHTYX/Era3D
• Single image to 6 multi-view images & normal maps with resolution: 512X512
• Note: you need at least 16GB vram to run this model
• Model weights: https://huggingface.co/pengHTYX/MacLab-Era3D-512-6view/tree/main

• InstantMesh Reconstruction Model: TencentARC/InstantMesh
• Sparse multi-view images with white background to 3D Mesh with RGB texture
• Works with arbitrary MVDiffusion models (Probably works best with Zero123++, but also works with CRM MVDiffusion model)
• Model weights: https://huggingface.co/TencentARC/InstantMesh/tree/main

• Zero123++: SUDO-AI-3D/zero123plus

• Single image to 6 view images with resolution: 320X320

• Convolutional Reconstruction Model: thu-ml/CRM

• Three stages pipeline:
  1. Single image to 6 view images (Front, Back, Left, Right, Top & Down)
  2. Single image & 6 view images to 6 same views CCMs (Canonical Coordinate Maps)
  3. 6 view images & CCMs to 3D mesh
• Note: For low vram pc, if you can't fit all three models for each stages into your GPU memory, then you can divide those three stages into different comfy workflow and run them separately
• Model weights: https://huggingface.co/sudo-ai/zero123plus-v1.2

• TripoSR: VAST-AI-Research/TripoSR | ComfyUI-Flowty-TripoSR
• Generate NeRF representation and using marching cube to turn it into 3D mesh
• Model weights: https://huggingface.co/stabilityai/TripoSR/tree/main
• [tripoSR-layered-diffusion workflow](https://github.com/C0nsumpt